Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification

Topic: Brain imaging, connectivity and assessment

Deep neural networks have led to state-of-the-art results in many medical imaging tasks including Alzheimer's disease (AD) detection based on structural magnetic resonance imaging (MRI) data. However, the network decisions are often perceived as being highly non-transparent, making it difficult to apply these algorithms in clinical routine. In this study, we propose using layer-wise relevance propagation (LRP) to visualize convolutional neural network decisions for AD based on MRI data. Similarly to other visualization methods, LRP produces a heatmap in the input space indicating the importance/relevance of each voxel contributing to the final classification outcome. In contrast to susceptibility maps produced by guided backpropagation ("Which change in voxels would change the outcome most?"), the LRP method is able to directly highlight positive contributions to the network classification in the input space. In particular, we show that (1) the LRP method is very specific for individuals ("Why does this person have AD?") with high inter-patient variability, (2) there is very little relevance for AD in healthy controls and (3) areas that exhibit a lot of relevance correlate well with what is known from literature. To quantify the latter, we compute size-corrected metrics of the summed relevance per brain area, e.g., relevance density or relevance gain. Although these metrics produce very individual "fingerprints" of relevance patterns for AD patients, a lot of importance is put on areas in the temporal lobe including the hippocampus. After discussing several limitations such as sensitivity toward the underlying model and computation parameters, we conclude that LRP might have a high potential to assist clinicians in explaining neural network decisions for diagnosing AD (and potentially other diseases) based on structural MRI data.

Key findings

• Deep neural networks have led to state-of-the-art results in many medical imaging tasks including Alzheimer's disease (AD) detection based on structural magnetic resonance imaging (MRI) data.
• After discussing several limitations such as sensitivity toward the underlying model and computation parameters, we conclude that LRP might have a high potential to assist clinicians in explaining neural network decisions for diagnosing AD (and potentially other diseases) based on structural MRI data.

New to this subject? Start with our plain-English guide: Digital health →

Study details

• Evidence strengthLow

Read the original

• DOI: 10.3389/fnagi.2019.00194
• PubMed: 31417397
• Original source →

Free copy unknown: no free-copy check has an answer for this record yet. That does not mean it is paywalled.

@article{bohle2019-31417397,
  author  = {Böhle, M. and Eitel, F. and Weygandt, M. and Ritter, K.},
  title   = {{Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification}},
  journal = {Frontiers in aging neuroscience},
  year    = {2019},
  doi     = {10.3389/fnagi.2019.00194},
  pmid    = {31417397},
  url     = {https://doi.org/10.3389/fnagi.2019.00194}
}

Related studies in Digital health tools

• Classification of Alzheimer's Disease Based on Eight-Layer Convolutional Neural Network with Leaky Rectified Linear Unit and Max Pooling Journal of medical systems · 2018-03-26 · usefulness score 41/100
• Automated classification of Alzheimer's disease and mild cognitive impairment using a single MRI and deep neural networks NeuroImage. Clinical · 2018-12-18 · usefulness score 48/100
• Transformer-based deep neural network language models for Alzheimer's disease risk assessment from targeted speech BMC medical informatics and decision making · 2021-03-09 · usefulness score 47/100
• MRI signatures of brain age and disease over the lifespan based on a deep brain network and 14 468 individuals worldwide Brain : a journal of neurology · 2020-07-01 · usefulness score 55/100
• Interpretable classification of Alzheimer's disease pathologies with a convolutional neural network pipeline Nature communications · 2019-05-15 · usefulness score 45/100
• Brain MRI analysis for Alzheimer's disease diagnosis using an ensemble system of deep convolutional neural networks Brain informatics · 2018-05-31 · usefulness score 41/100

Similar studies

• Biomarker fidelity score: A quantitative framework for individual-level validation of explainability methods in 3D Alzheimer’s disease MRI classification 2026 · Long-term cohort studies
• Deep learning detection of informative features in tau PET for Alzheimer’s disease classification 2020 · Brain scans and imaging
• Classification and Visualization of Alzheimer’s Disease using Volumetric Convolutional Neural Network and Transfer Learning 2019 · Brain scans and imaging
• Multimodal deep learning for Alzheimer's disease dementia assessment 2022 · Digital health tools
• Neuron-level explainable AI for Alzheimer's Disease assessment from fundus images 2024 · Brain scans and imaging
• Multimodal deep learning models for early detection of Alzheimer's disease stage 2021 · Digital health tools

More on Digital health tools

• A review that covers this ground GABAergic dysfunction, neural network hyperactivity and memory impairments in human aging and Alzheimer's disease Seminars in cell & developmental biology · 2021-02-09 · usefulness score 43/100
• Newest in this subject Speaker-Wise Dementia Screening fromNaturalistic Speech with Lexical Entropy, Semantic Drift, and Multimodal Fusion Research Square · 2026-10-21 · Preprint — not yet peer-reviewed · usefulness score 16/100
• Newest in this subject Integrating Multisource Target Evidence with Machine-Learning Potency Prediction for Alzheimer’s Disease Drug Discovery bioRxiv · 2026-10-20 · Preprint — not yet peer-reviewed · usefulness score 16/100

See all studies in Digital health tools →